© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 21-GEMMASCOPE-TRANSCODER-16K
    7. 3105
    Prev
    Next
    INDEX
    Explanations

    sentences that describe a sports game and injuries

    oai_token-act-pair · gemini-2.0-flash

    titles or roles related to medical staff in sports

    np_token-act-pair-logits · gpt-4o-mini

    sports injuries

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_21/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    FromString
    -0.55
     تضيفلها
    -0.55
    forChild
    -0.54
     betale
    -0.54
    durch
    -0.52
    ALF
    -0.50
    inerja
    -0.49
    niająca
    -0.48
    ALLA
    -0.48
    WEBPACK
    -0.48
    POSITIVE LOGITS
     trainers
    0.81
     Trainers
    0.78
     trainer
    0.78
     MotionEvent
    0.68
     Trainer
    0.66
    Trainer
    0.63
    trainer
    0.63
     تعدى
    0.62
    TestTools
    0.55
     GenerationType
    0.55
    Activations Density 1.307%

    No Known Activations